Mühendislik Fakültesi / Faculty of Engineering

Permanent URI for this collectionhttps://hdl.handle.net/11727/1401

Browse

Filters

20162

Settings

Author: search.filters.author.Ergun, HilalSubject: search.filters.subject.Deep learning

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Feature-level Fusion of Convolutional Neural Networks for Visual Object Classification
    (2016) Ergun, Hilal; Sert, Mustafa; https://orcid.org/0000-0002-7056-4245; AAB-8673-2019
    Deep learning architectures have shown great success in various computer vision applications. In this study, we investigate some of the very popular convolutional neural network (CNN) architectures, namely GoogleNet, AlexNet, VGG19 and ResNet. Furthermore, we show possible early feature fusion strategies for visual object classification tasks. Concatanation of features, average pooling and maximum pooling are among the investigated fusion strategies. We obtain state-of-the-art results on well-known image classification datasets of Caltech-101, Caltech-256 and Pascal VOC 2007.
  • No Thumbnail Available
    Item
    Early and Late Level Fusion of Deep Convolutional Neural Networks for Visual Concept Recognition
    (2016) Ergun, Hilal; Akyuz, Yusuf Caglar; Sert, Mustafa; Liu, Jianquan; 0000-0002-7056-4245; 0000-0002-7056-4245; B-1296-2011; D-3080-2015; AAB-8673-2019
    Visual concept recognition is an active research field in the last decade. Related to this attention, deep learning architectures are showing great promise in various computer vision domains including image classification, object detection, event detection and action recognition in videos. In this study, we investigate various aspects of convolutional neural networks for visual concept recognition. We analyze recent studies and different network architectures both in terms of running time and accuracy. In our proposed visual concept recognition system, we first discuss various important properties of popular convolutional network architecture under consideration. Then we describe our method for feature extraction at different levels of abstraction. We present extensive empirical information along with best practices for big data practitioners. Using these best practices we propose efficient fusion mechanisms both for single and multiple network models. We present state-of-the-art results on benchmark datasets while keeping computational costs at low level. Our results show that these state-of-the-art results can be reached without using extensive data augmentation techniques.